%0 Journal Article
%T Human Limb Segmentation in Depth Maps based on Spatio-Temporal Graph Cuts Optimization
%A Antonio Hernandez
%A Nadezhda Zlateva
%A Alexander Marinov
%A Miguel Reyes
%A Petia Radeva
%A Dimo Dimov
%A Sergio Escalera
%J Journal of Ambient Intelligence and Smart Environments
%D 2012
%V 4
%N 6
%@ 1876-1364
%F Antonio Hernandez2012
%O MILAB;HuPBA
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2006), last updated on Thu, 13 Mar 2014 13:22:43 +0100
%X We present a framework for object segmentation using depth maps based on Random Forest and Graph-cuts theory, and apply it to the segmentation of human limbs. First, from a set of random depth features, Random Forest is used to infer a set of label probabilities for each data sample. This vector of probabilities is used as unary term in α−β swap Graph-cuts algorithm. Moreover, depth values of spatio-temporal neighboring data points are used as boundary potentials. Results on a new multi-label human depth data set show high performance in terms of segmentation overlapping of the novel methodology compared to classical approaches.
%K Multi-modal vision processing
%K Random Forest
%K Graph-cuts
%K multi-label segmentation
%K human body segmentation
%U http://refbase.cvc.uab.es/files/HZM2012a.pdf
%U http://dx.doi.org/10.3233/AIS-2012-0176
%P 535-546